MHGanainy/16-clusters-balanced-12

README.md

@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 # 16-clusters-balanced-12
 
 This model is a fine-tuned version of [openai-community/gpt2-xl](https://huggingface.co/openai-community/gpt2-xl) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.7484
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.748362421989441,
+    "eval_runtime": 19.8411,
+    "eval_samples_per_second": 13.759,
+    "eval_steps_per_second": 1.764,
+    "perplexity": 5.745186776942814,
+    "total_flos": 1.9945113944064e+16,
+    "train_loss": 2.004207673620005,
+    "train_runtime": 342.6727,
+    "train_samples_per_second": 6.406,
+    "train_steps_per_second": 3.204
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.748362421989441,
+    "eval_runtime": 19.8411,
+    "eval_samples_per_second": 13.759,
+    "eval_steps_per_second": 1.764,
+    "perplexity": 5.745186776942814
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 1.9945113944064e+16,
+    "train_loss": 2.004207673620005,
+    "train_runtime": 342.6727,
+    "train_samples_per_second": 6.406,
+    "train_steps_per_second": 3.204
+}

trainer_state.json

@@ -0,0 +1,112 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1098,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09107468123861566,
+      "grad_norm": 0.0878501608967781,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 2.3384,
+      "step": 100
+    },
+    {
+      "epoch": 0.18214936247723132,
+      "grad_norm": 0.21773786842823029,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 2.3195,
+      "step": 200
+    },
+    {
+      "epoch": 0.273224043715847,
+      "grad_norm": 0.3442952334880829,
+      "learning_rate": 2e-05,
+      "loss": 2.2497,
+      "step": 300
+    },
+    {
+      "epoch": 0.36429872495446264,
+      "grad_norm": 0.4830267131328583,
+      "learning_rate": 1.9235024449252306e-05,
+      "loss": 2.093,
+      "step": 400
+    },
+    {
+      "epoch": 0.4553734061930783,
+      "grad_norm": 0.6537724137306213,
+      "learning_rate": 1.705713531565757e-05,
+      "loss": 2.0122,
+      "step": 500
+    },
+    {
+      "epoch": 0.546448087431694,
+      "grad_norm": 0.8363291621208191,
+      "learning_rate": 1.37995389871036e-05,
+      "loss": 1.911,
+      "step": 600
+    },
+    {
+      "epoch": 0.6375227686703097,
+      "grad_norm": 1.0528734922409058,
+      "learning_rate": 9.96063177270025e-06,
+      "loss": 1.8757,
+      "step": 700
+    },
+    {
+      "epoch": 0.7285974499089253,
+      "grad_norm": 0.871990978717804,
+      "learning_rate": 6.127747704569016e-06,
+      "loss": 1.8279,
+      "step": 800
+    },
+    {
+      "epoch": 0.819672131147541,
+      "grad_norm": 0.9544081091880798,
+      "learning_rate": 2.8872993029040506e-06,
+      "loss": 1.8181,
+      "step": 900
+    },
+    {
+      "epoch": 0.9107468123861566,
+      "grad_norm": 0.9045562148094177,
+      "learning_rate": 7.350593278519824e-07,
+      "loss": 1.81,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "step": 1098,
+      "total_flos": 1.9945113944064e+16,
+      "train_loss": 2.004207673620005,
+      "train_runtime": 342.6727,
+      "train_samples_per_second": 6.406,
+      "train_steps_per_second": 3.204
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1098,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.9945113944064e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}